Metro AI Apps Recipe — DLSPS + WebRTC + Mosquitto + Node-RED + Grafana + Nginx

Build an end-to-end {{OBJECT}}-analytics stack on Intel hardware in ./{{STACK_DIR}}/ with Docker Compose. Vertical-agnostic: the same seven-container topology (Nginx, DLSPS, Mosquitto, Node-RED, Grafana, MediaMTX, Coturn) serves any DL Streamer / OpenVINO CV pipeline — only the model, class filter, alert rule, dashboard, and topic names differ. Follows the open-edge-platform Metro Vision AI App Recipe MediaMTX + Coturn + WebRTC path, streamlined (no Prometheus/OTel). SceneScape is off by default — opt-in multi-camera spatial analysis (references/SCENESCAPE.md). Detection metadata flows DLSPS→MQTT→Node-RED→Grafana; video is decoupled (DLSPS overlays via gvawatermark, pushes each source to MediaMTX over WHIP, ENABLE_WEBRTC=true, per-source peer-id) — see architecture below.

When to use this skill